Data-driven probabilistic surrogate model for floating wind turbine lifetime damage equivalent load prediction
Preprint
- 21 February 2025
- preprint
- Published by Copernicus GmbH in EGUsphere
- Vol. 2025, 1-33
Abstract
Floating offshore wind turbines experience complex hydrodynamic and aerodynamic loading influenced by substructure types and stochastic environmental conditions. Accurately estimating the lifetime fatigue loads requires analyzing thousands of operational scenarios, leading to high computational costs. Moreover, choosing the right input features driving fatigue in floating wind systems and appropriately binning them still remains an open question. We present a fast probabilistic surrogate that maps the site conditions to the loads on the wind turbine. The probabilistic aspect allows the propagation and quantification of statistical uncertainties from the stochastic input quantities on the resulting loads. A fast surrogate eliminates the need to fit a distribution to the site conditions or bin the input data. Rather, all available met-ocean data can be directly used as input, which automatically accounts for the joint distribution in the calculations. The surrogate model in this study uses the mixture density network (MDN) to predict the conditional distribution of the 10-minute damage equivalent loads (DELs) for a 6 MW spar-type floating wind turbine. The MDN achieves high accuracy (R2 > 0.99) in capturing DEL means while efficiently propagating the statistical uncertainties. Furthermore, the surrogate enables quick estimation of 25-year lifetime fatigue damage across a range of potential floating wind farm sites, demonstrating its capability to facilitate rapid decision-making during preliminary site analysis.Keywords
All Related Versions
- Published version: Wind Energy Science, 10 (12), 2865.
Funding Information
- H2020 Marie Skłodowska-Curie Actions (860737)
This publication has 37 references indexed in Scilit:
- Global sensitivity analysis of a semi-submersible floating wind turbine using a neural network fitting methodOcean Engineering, 2023
- Impacts of water depth increase on offshore floating wind turbine dynamicsOcean Engineering, 2021
- Parametric hierarchical kriging for multi-fidelity aero-servo-elastic simulators — Application to extreme loads on wind turbinesProbabilistic Engineering Mechanics, 2019
- Uncertainty propagation through an aeroelastic wind turbine model using polynomial surrogatesRenewable Energy, 2018
- Hierarchical four-step global sensitivity analysis of offshore wind turbines based on aeroelastic time domain simulationsRenewable Energy, 2017
- Analysis of the design of experiments of offshore wind turbine fatigue reliability design with Kriging surfacesProcedia Structural Integrity, 2017
- Neural Networks: Tricks of the Trade2012
- The Wasserstein distances2009
- On Early Stopping in Gradient Descent LearningConstructive Approximation, 2007
- On the distribution of points in a cube and the approximate evaluation of integralsUSSR Computational Mathematics and Mathematical Physics, 1967